AUTHOR=Vélez-Cruz Nayely , Papandreou-Suppappola Antonia 

TITLE=Bayesian learning of nonlinear gene regulatory networks with switching architectures

JOURNAL=Frontiers in Signal Processing

VOLUME=Volume 4 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/signal-processing/articles/10.3389/frsip.2024.1323538

DOI=10.3389/frsip.2024.1323538

ISSN=2673-8198

ABSTRACT=Gene regulatory networks (GRNs) are characterized by their dynamicity, meaning that the regulatory interactions which constitute these networks evolve with time. Understanding when changes in the GRN architecture occur can inform our understanding of fundamental biological processes, such as disease manifestation, development, and evolution. However, it is usually not possible to know a priori when a change in the network architecture will occur. Furthermore, an architectural shift may change the underlying noise characteristics, such as the process noise covariance. In this work, we develop a fully Bayesian hierarchical model to account for the following: (a) sudden changes in the network architecture; (b) unknown process noise covariance which may change along with the network structure; and (c) unknown measurement noise covariance. We exploit the use of conjugate priors to develop an analytically tractable inference scheme using Bayesian sequential Monte Carlo (SMC) methods with a local Gibbs sampler. We demonstrate the efficacy of our Bayesian learning algorithm by estimating the unknown and time-varying gene expression levels and architectural model indicator.